Improve/skill review optimization#12
Open
rohan-tessl wants to merge 3 commits intoMadAppGang:mainfrom
Open
Conversation
Hey 👋 @erudenko I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | claudemem-orchestration | 0% | 80% | +80% | | claudemem-search | 0% | 70% | +70% | | claudish-integration | 0% | 69% | +69% | | sequence-best-practices | 44% | 100% | +56% | | email-deliverability | 43% | 96% | +53% | | ab-testing-patterns | 44% | 96% | +52% | | campaign-metrics | 48% | 100% | +52% | | setup | 35% | 81% | +46% | | status | 48% | 93% | +45% | | proof-of-work | 49% | 93% | +44% | | state-machine | 47% | 89% | +42% | | task-complexity-router | 59% | 100% | +41% | | deep-analysis | 56% | 96% | +40% | | analytics-interpretation | 49% | 89% | +40% | | data-extraction-patterns | 49% | 89% | +40% | | search-interceptor | 55% | 93% | +38% | | help | 43% | 81% | +38% | | revert | 48% | 85% | +37% | | brainstorming | 40% | 77% | +37% | | ultrathink-detective | 60% | 96% | +36% | | ui-analyse | 50% | 86% | +36% | | architect-detective | 65% | 100% | +35% | | error-recovery | 65% | 100% | +35% | | performance-correlation | 49% | 84% | +35% | | statusline-customization | 60% | 94% | +34% | | developer-detective | 66% | 100% | +34% | | implement | 55% | 89% | +34% | | new-track | 55% | 89% | +34% | | tag-command-mapping | 55% | 89% | +34% | | code-search-selector | 68% | 100% | +32% | | linear-integration | 66% | 96% | +30% | | link-strategy | 59% | 89% | +30% | | gemini-api | 61% | 90% | +29% | | session-isolation | 64% | 93% | +29% | | error-handling | 56% | 83% | +27% | | bunjs-architecture | 61% | 86% | +25% | | cross-plugin-detective | 63% | 88% | +25% | | ui-implement | 57% | 81% | +24% | | multi-agent-coordination | 65% | 89% | +24% | | dependency-check | 55% | 78% | +23% | | quality-gates | 70% | 93% | +23% | | serp-analysis | 66% | 89% | +23% | | yaml-agent-format | 66% | 89% | +23% | | design-references | 59% | 81% | +22% | | investigate | 54% | 76% | +22% | | performance-tracking | 64% | 86% | +22% | | context-detection | 54% | 74% | +20% | | style-format | 61% | 81% | +20% | | debugging-strategies | 61% | 79% | +18% | | testing-strategies | 61% | 79% | +18% | | ui-design-review | 66% | 83% | +17% | | claudish-usage (bun) | 66% | 81% | +15% | | auth-patterns | 65% | 79% | +14% | | css-modules | 70% | 83% | +13% | | documentation-standards | 57% | 71% | +14% | | python | 65% | 79% | +14% | | rust | 69% | 83% | +14% | | testing-frontend | 69% | 83% | +14% | | universal-patterns | 46% | 60% | +14% | | optimize | 55% | 64% | +9% | | xml-standards | 74% | 83% | +9% | | claudish-usage (shared) | 76% | 81% | +5% | | test-coverage | 59% | 64% | +5% | | ui-style-format | 63% | 68% | +5% | | database-patterns | 69% | 71% | +2% | 65 skills improved across 10 plugins, average improvement +30% (55% → 85%). Changes made: - Added missing YAML frontmatter to claudish-integration - Fixed invalid frontmatter in claudemem-orchestration and claudemem-search - Converted description formats to quoted strings with "Use when..." triggers - Added natural language trigger terms for better skill discovery - Removed unknown frontmatter keys (version, tags, keywords, plugin, updated) - Added numbered workflow steps with validation checkpoints - Added copy-paste ready code examples - Improved progressive disclosure - Reduced verbosity Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute. Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices and ask it to optimize your skill. Ping me - @rohan-tessl - if you hit any snags. Thanks in advance 🙏
Further improvements from extended review: - debug-mode: 75% → 100% (condensed to ~90 lines with workflow) - browser-debugger: 64% → 100% (condensed to ~110 lines with vision model table) - dependency-check: 55% → 100% (improved trigger terms) - openrouter-trending-models: 71% → 100% (condensed with jq examples) Total: 68 skills improved, 12 at 100%, avg +30% (56% → 86%)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @ninehills 👋
I ran your skills through
tessl skill reviewat work and found some targeted improvements.Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.
Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide and ask it to optimize your skill. Ping me - @rohan-tessl - if you hit any snags.
Thanks in advance 🙏